Exploring Transfer Learning on Face Recognition of Dark Skinned, Low Quality and Low Resource Face Data

TL;DR

This study investigates the effectiveness of transfer learning on low-quality, low-resource dark-skinned face datasets, demonstrating high accuracy in recognizing Ethiopian faces despite limited data.

Contribution

It is the first to evaluate transfer learning on dark-skinned face recognition with low-quality, low-resource data, showing promising results.

Findings

Achieved over 95% accuracy in recognizing dark-skinned faces

Transfer learning effectively adapts to low-quality, low-resource datasets

Demonstrates potential for improving dark-skinned face recognition systems

Abstract

There is a big difference in the tone of color of skin between dark and light skinned people. Despite this fact, most face recognition tasks almost all classical state-of-the-art models are trained on datasets containing an overwhelming majority of light skinned face images. It is tedious to collect a huge amount of data for dark skinned faces and train a model from scratch. In this paper, we apply transfer learning on VGGFace to check how it works on recognising dark skinned mainly Ethiopian faces. The dataset is of low quality and low resource. Our experimental results show above 95\% accuracy which indicates that transfer learning in such settings works.